English
Related papers

Related papers: PositNN: Training Deep Neural Networks with Mixed …

200 papers

Diffusion models are emerging models that generate images by iteratively denoising random Gaussian noise using deep neural networks. These models typically exhibit high computational and memory demands, necessitating effective post-training…

Computer Vision and Pattern Recognition · Computer Science 2024-08-14 Cheng Chen , Christina Giannoula , Andreas Moshovos

Deep neural networks (DNNs) are state-of-the-art algorithms for multiple applications, spanning from image classification to speech recognition. While providing excellent accuracy, they often have enormous compute and memory requirements.…

Machine Learning · Computer Science 2020-11-12 Ussama Zahid , Giulio Gambardella , Nicholas J. Fraser , Michaela Blott , Kees Vissers

Recent research implies that training and inference of deep neural networks (DNN) can be computed with low precision numerical representations of the training/test data, weights and gradients without a general loss in accuracy. The benefit…

Computer Vision and Pattern Recognition · Computer Science 2017-10-17 Dominik Marek Loroch , Norbert Wehn , Franz-Josef Pfreundt , Janis Keuper

The majority of the research on the quantization of Deep Neural Networks (DNNs) is focused on reducing the precision of tensors visible by high-level frameworks (e.g., weights, activations, and gradients). However, current hardware still…

Machine Learning · Computer Science 2024-01-26 Yaniv Blumenfeld , Itay Hubara , Daniel Soudry

Deep learning is finding its way into high energy physics by replacing traditional Monte Carlo simulations. However, deep learning still requires an excessive amount of computational resources. A promising approach to make deep learning…

Data Analysis, Statistics and Probability · Physics 2021-03-19 Florian Rehm , Sofia Vallecorsa , Vikram Saletore , Hans Pabst , Adel Chaibi , Valeriu Codreanu , Kerstin Borras , Dirk Krücker

Large DNNs with mixed-precision quantization can achieve ultra-high compression while retaining high classification performance. However, because of the challenges in finding an accurate metric that can guide the optimization process, these…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Souvik Kundu , Shikai Wang , Qirui Sun , Peter A. Beerel , Massoud Pedram

Deep neural networks have revolutionized the field of machine learning by providing unprecedented human-like performance in solving many real-world problems such as image and speech recognition. Training of large DNNs, however, is a…

Emerging Technologies · Computer Science 2017-12-05 Nandakumar S. R. , Manuel Le Gallo , Irem Boybat , Bipin Rajendran , Abu Sebastian , Evangelos Eleftheriou

By quantizing network weights and activations to low bitwidth, we can obtain hardware-friendly and energy-efficient networks. However, existing quantization techniques utilizing the straight-through estimator and piecewise constant…

Machine Learning · Computer Science 2024-07-24 Hiroyuki Tokunaga , Joel Nicholls , Daria Vazhenina , Atsunori Kanemura

Winograd convolution is widely used in deep neural networks (DNNs). Existing work for DNNs considers only the subset Winograd algorithms that are equivalent to Toom-Cook convolution. We investigate a wider range of Winograd algorithms for…

Machine Learning · Computer Science 2019-06-26 Barbara Barabasz , David Gregg

Information loss in numerical physics simulations can arise from various sources when solving discretized partial differential equations. In particular, errors related to numerical precision ("sub-precision errors") can accumulate in the…

Fluid Dynamics · Physics 2022-09-27 Akash Haridas , Nagabhushana Rao Vadlamani , Yuki Minamoto

Deep learning models have achieved significant success in various image related tasks. However, they often encounter challenges related to computational complexity and overfitting. In this paper, we propose an efficient approach that…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Salim Khazem , Jeremy Fix , Cédric Pradalier

Deep Neural Networks (DNNs) are computationally and memory intensive, which makes their hardware implementation a challenging task especially for resource constrained devices such as IoT nodes. To address this challenge, this paper…

Computer Vision and Pattern Recognition · Computer Science 2021-05-10 Mohammed F. Tolba , Huruy Tekle Tesfai , Hani Saleh , Baker Mohammad , Mahmoud Al-Qutayri

State of the art deep learning models have made steady progress in the fields of computer vision and natural language processing, at the expense of growing model sizes and computational complexity. Deploying these models on low power and…

Machine Learning · Computer Science 2018-10-29 Meghan Cowan , Thierry Moreau , Tianqi Chen , Luis Ceze

Binary Neural Networks (BNNs) enable efficient deep learning by saving on storage and computational costs. However, as the size of neural networks continues to grow, meeting computational requirements remains a challenge. In this work, we…

Machine Learning · Computer Science 2024-07-18 Matt Gorbett , Hossein Shirazi , Indrakshi Ray

Compression of large and performant vision foundation models (VFMs) into arbitrary bit-wise operations (BitOPs) allows their deployment on various hardware. We propose to fine-tune a VFM to a mixed-precision quantized supernet. The…

Computer Vision and Pattern Recognition · Computer Science 2024-04-01 Yuiko Sakuma , Masakazu Yoshimura , Junji Otsuka , Atsushi Irie , Takeshi Ohashi

Deep neural networks have achieved state-of-the-art results in a wide range of applications, from natural language processing and computer vision to speech recognition. However, as tasks become increasingly complex, model sizes continue to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Tomer Gafni , Asaf Karnieli , Yair Hanani

Over the last few years, neural networks have started penetrating safety critical systems to take decisions in robots, rockets, autonomous driving car, etc. A problem is that these critical systems often have limited computing resources.…

Software Engineering · Computer Science 2022-02-24 Hanane Benmaghnia , Matthieu Martel , Yassamine Seladji

The study of the expressive power of neural networks has investigated the fundamental limits of neural networks. Most existing results assume real-valued inputs and parameters as well as exact operations during the evaluation of neural…

Machine Learning · Computer Science 2024-07-17 Yeachan Park , Geonho Hwang , Wonyeol Lee , Sejun Park

It is known that training deep neural networks, in particular, deep convolutional networks, with aggressively reduced numerical precision is challenging. The stochastic gradient descent algorithm becomes unstable in the presence of noisy…

Machine Learning · Computer Science 2016-07-11 Darryl D. Lin , Sachin S. Talathi

As LLMs scale, low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. In this work, we evaluate HiFloat (HiF8 and HiF4), a family of formats tailored for Ascend NPUs. Through rigorous…

Computation and Language · Computer Science 2026-03-03 Pengxiang Zhao , Hui-Ling Zhen , Xing Li , Han Bao , Weizhe Lin , Zhiyuan Yang , Manyi Zhang , Yuanyong Luo , Ziwei Yu , Xin Wang , Mingxuan Yuan , Xianzhi Yu , Zhenhua Dong